rdk-embodied-lerobot

rdk-embodied-lerobot is a skill for Claude Code, Codex from D-Robotics/moss. It costs 297 tokens per session (3,677 once invoked), scanned A, original, MIT.

A deployment guide for running trained LeRobot ACT imitation policies or Pi0 VLA robot-control models on RDK S-series boards. ACT learns actions from demonstrations, while a VLA model connects visual input and language with robot actions.

In plain words
What is it for?
Use it to export ACT or Pi0 policies to ONNX, compile them to .hbm, and run the control loop that drives a robot arm.
Why use it?
The board cannot run the original PyTorch checkpoint or raw ONNX policy directly. The policy must be exported, compiled into an .hbm BPU file, and supplied with its normalization data.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to export ACT or Pi0 policies to ONNX, compile them to .hbm, and run the control loop that drives a robot arm.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/d-robotics/moss/rdk-embodied-lerobot
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add D-Robotics/moss --skill rdk-embodied-lerobot
Clone the repo
git clone --depth 1 https://github.com/D-Robotics/moss

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for rdk-embodied-lerobot

README.md
[![agentmods](https://agentmods.dev/badge/skills/d-robotics/moss/rdk-embodied-lerobot/github.svg)](https://agentmods.dev/skills/d-robotics/moss/rdk-embodied-lerobot)
Your own site
<a href="https://agentmods.dev/skills/d-robotics/moss/rdk-embodied-lerobot"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/rdk-embodied-lerobot/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for rdk-embodied-lerobot

Your own site · 80×15
<a href="https://agentmods.dev/skills/d-robotics/moss/rdk-embodied-lerobot"><img src="https://agentmods.dev/badge/skills/d-robotics/moss/rdk-embodied-lerobot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 297 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,677 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 90
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00297 $0.03677
Opus 5 $0.00148 $0.01839
Sonnet 5 $0.00059 $0.00735
Haiku 4.5 $0.00030 $0.00368

Measured 10d ago against content hash e4604b0aae4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

rdk-embodied-lerobot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/moss-agent/assets/rdk-knowledge/skills/rdk-embodied-lerobot/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RDK Embodied AI: LeRobot ACT & Pi0 VLA Deployment

Take a trained robot-control policy and run it on an RDK board's BPU: a LeRobot ACT imitation policy, or a Pi0 / openpi VLA model. This skill owns the software deployment half only — exporting a checkpoint to ONNX, compiling it to .hbm in the OpenExplorer (OE) Docker toolchain, and running the on-board control loop.

The single most important thing: a board can only run an OE-compiled .hbm. It cannot run a raw .pt/ONNX policy, and the on-board control script (bpu_control_robot.py) loads .hbm + .npy normalization files, never the PyTorch checkpoint. If the user copied a checkpoint to the board expecting it to drive the arm, stop and route them through the export→compile loop first.

Sources: official D-Robotics repos rdk_LeRobot_tools (stable / s100 / s600 branches), openpi_runtime (develop), huggingface.co/D-Robotics/openpi. Every non-trivial claim below is verified against those READMEs/scripts.

Scope boundary — read this before answering

This skill covers trained policy → BPU → on-board control loop ONLY.

  • ✅ In scope: export ACT to ONNX, compile to .hbm, board-side hbm-runtime / C++ BPU runtime, bpu_control_robot.py, Pi0 client-server runtime.
  • ❌ Out of scope (it's upstream LeRobot, not this repo): SO-101/SO-100 arm assembly, motor ID setup, zero-point calibration (lerobot-calibrate), teleoperation data collection (lerobot-record), ACT training (lerobot-train), serial ports/baud. Point the user to huggingface/lerobot and the SO-101 docs for that front half.

Which path / which branch (decision cheat-sheet)

Pick the path first, then the branch — they pin different LeRobot versions and toolchain settings.

Goal Path Repo + branch Board march LeRobot
ACT on S100, current ACT rdk_LeRobot_tools s100 S100 (Nash-e) nash-e upstream HF v0.5.2
ACT on S600, current ACT rdk_LeRobot_tools s600 S600 (Nash) nash-p upstream HF v0.5.2
ACT, legacy v2.1 datasets ACT rdk_LeRobot_tools stable S100 nash-e D-Robotics fork
Pi0 VLA dual-arm VLA openpi_runtime develop S600 (Nash) (pre-quantized HBM) n/a

Read the full file on GitHub · 119 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 119 lines · 297 tokens per session scan A e4604b0aae4a

Subscribe to this mod's changes

rdk-embodied-lerobot is a skill published in the GitHub repository D-Robotics/moss (142 stars, last pushed 14d ago), licensed MIT. It adds 297 tokens to every session and 3,677 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-memory-thermal-ops

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

wshobson/agents · 59 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

minicpm5-deploy-vllm-ascend

Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torchnpu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.

OpenBMB/MiniCPM · 87 tokens

amc-run-rtsp-calibration

Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.

NVIDIA/skills · 59 tokens